Berkman case

Building Lasting ML: from audit to service


Berkman trades and supplies fuel to customers with its network of 85 gas stations. As a family owned company, their values are to stay personal and be reliable to their customers.

The Business:

Berkman Energy Service is a family owned business since 1903 that is currently in the hands of the 4th generation. Started in 1903 as a charcoal supplier, ‘Kolenhandel De Moriaan’‚Äč in Barendrecht. They are now the largest independent trader of fuel in the Netherlands with about 130 employees, and a network of 85 gas stations.


Their Challenge:

Each day, Berkman receives in the order of a hundred different purchasing prices from their suppliers. These prices are dependent on volatile market movements. Using the market as a predictor for the most optimal buying decision, Berkman can get the best prices at the best time of the day and as a result increase their margin. Collecting all the prices and doing the decision making manually is labour intensive and increases the risk of not choosing the best prices at the best time.


Our Solution:

Machine Learning flow

Enijns created an automated decision support system that automatically reads all the prices, makes calculations, and stores the prices in a database. These prices are then visualised on a PowerBI dashboard to see the lowest prices at each moment of the day. By collecting the supplier prices and market movements, we are able to forecast near realtime price movements. Enjins developed a system to act on these forecasts and decide on the best buying strategy for the upcoming 24 hours. Ultimately, the goal is to have a simulation model that incorporates all the variables that come to play (such as logistics, and consumer behaviour) to select the most optimal moment for buying and the most optimal price for selling.

Way of working:

At Berkman we have successfully incorporated the full cycle of getting ML in production. At Enjins this life cycle consist out of three distinct phases as shown in the figure above. We believe that these phases are essential when building lasting ML applications. The model makes predictions based on data input variables that can change over time. Therefore, we provide service to keep the models operational so Berkman can rely on a system that is working correctly.

Get in touch

Curious to find out what Machine Learning can do for you?

Don’t hesitate to fill out the contact form and get in touch.


Contact Go to careers

Enjins logo


De Entree 234
1101 EE Amsterdam

KvK: 71755101

We would like to hear from you